[R-sig-Epi] Global prevalence

[Adam Cohen]

I am using the R package, but my question is towards method rather than
application in R. I am a doctor with some programming experience but no
worthy experience in epidemiology /  statistics. If this is inappropriate
for this mailing list i apologize.

I am looking for which overall statistical methods I should explore and try
to utilize. So I am looking for key words if that is possible, not for
someone to do the job for me.

I am estimating a global prevalence estimate of a disease. I have x number
of studies, each with a given prevalence proportion. The studies are from
different countries, there is a continuous variable that is known for each
country that affects disease prevalence.  Populations in the studies have
different age means and intervals. Age is known to affect disease
prevalence. Might also want to include categorical information as well as
year the study was performed.

I assume it is possible to create a mathematical model that, given the data
from the studies, can estimate prevalence at any combination of the
variable values mentioned, so that this model can be standardized to the
 global situation today. Is there some subcategory in random effects
analysis I should look into or something else entirely?

Best regards
Adam Cohen

	[[alternative HTML version deleted]]